Show More
@@ -1,204 +1,212 b'' | |||
|
1 | 1 | # coding: utf-8 |
|
2 | 2 | """String filters. |
|
3 | 3 | |
|
4 | 4 | Contains a collection of useful string manipulation filters for use in Jinja |
|
5 | 5 | templates. |
|
6 | 6 | """ |
|
7 | 7 | #----------------------------------------------------------------------------- |
|
8 | 8 | # Copyright (c) 2013, the IPython Development Team. |
|
9 | 9 | # |
|
10 | 10 | # Distributed under the terms of the Modified BSD License. |
|
11 | 11 | # |
|
12 | 12 | # The full license is in the file COPYING.txt, distributed with this software. |
|
13 | 13 | #----------------------------------------------------------------------------- |
|
14 | 14 | |
|
15 | 15 | #----------------------------------------------------------------------------- |
|
16 | 16 | # Imports |
|
17 | 17 | #----------------------------------------------------------------------------- |
|
18 | 18 | |
|
19 | 19 | import os |
|
20 | 20 | import re |
|
21 | 21 | import textwrap |
|
22 | 22 | try: |
|
23 | 23 | from urllib.parse import quote # Py 3 |
|
24 | 24 | except ImportError: |
|
25 | 25 | from urllib2 import quote # Py 2 |
|
26 | 26 | from xml.etree import ElementTree |
|
27 | 27 | |
|
28 | 28 | from IPython.core.interactiveshell import InteractiveShell |
|
29 | 29 | from IPython.utils import py3compat |
|
30 | 30 | |
|
31 | 31 | #----------------------------------------------------------------------------- |
|
32 | 32 | # Functions |
|
33 | 33 | #----------------------------------------------------------------------------- |
|
34 | 34 | |
|
35 | 35 | __all__ = [ |
|
36 | 36 | 'wrap_text', |
|
37 | 37 | 'html2text', |
|
38 | 38 | 'add_anchor', |
|
39 | 39 | 'strip_dollars', |
|
40 | 40 | 'strip_files_prefix', |
|
41 | 41 | 'comment_lines', |
|
42 | 42 | 'get_lines', |
|
43 | 43 | 'ipython2python', |
|
44 | 44 | 'posix_path', |
|
45 | 45 | 'path2url', |
|
46 | 46 | 'add_prompts' |
|
47 | 47 | ] |
|
48 | 48 | |
|
49 | 49 | |
|
50 | 50 | def wrap_text(text, width=100): |
|
51 | 51 | """ |
|
52 | 52 | Intelligently wrap text. |
|
53 | 53 | Wrap text without breaking words if possible. |
|
54 | 54 | |
|
55 | 55 | Parameters |
|
56 | 56 | ---------- |
|
57 | 57 | text : str |
|
58 | 58 | Text to wrap. |
|
59 | 59 | width : int, optional |
|
60 | 60 | Number of characters to wrap to, default 100. |
|
61 | 61 | """ |
|
62 | 62 | |
|
63 | 63 | split_text = text.split('\n') |
|
64 | 64 | wrp = map(lambda x:textwrap.wrap(x,width), split_text) |
|
65 | 65 | wrpd = map('\n'.join, wrp) |
|
66 | 66 | return '\n'.join(wrpd) |
|
67 | 67 | |
|
68 | 68 | |
|
69 | 69 | def html2text(element): |
|
70 | 70 | """extract inner text from html |
|
71 | 71 | |
|
72 | 72 | Analog of jQuery's $(element).text() |
|
73 | 73 | """ |
|
74 | 74 | if isinstance(element, py3compat.string_types): |
|
75 | try: | |
|
75 | 76 | element = ElementTree.fromstring(element) |
|
77 | except Exception: | |
|
78 | # failed to parse, just return it unmodified | |
|
79 | return element | |
|
76 | 80 | |
|
77 | 81 | text = element.text or "" |
|
78 | 82 | for child in element: |
|
79 | 83 | text += html2text(child) |
|
80 | 84 | text += (element.tail or "") |
|
81 | 85 | return text |
|
82 | 86 | |
|
83 | 87 | |
|
84 | 88 | def add_anchor(html): |
|
85 | 89 | """Add an anchor-link to an html header tag |
|
86 | 90 | |
|
87 | 91 | For use in heading cells |
|
88 | 92 | """ |
|
93 | try: | |
|
89 | 94 | h = ElementTree.fromstring(py3compat.cast_bytes_py2(html, encoding='utf-8')) |
|
95 | except Exception: | |
|
96 | # failed to parse, just return it unmodified | |
|
97 | return html | |
|
90 | 98 | link = html2text(h).replace(' ', '-') |
|
91 | 99 | h.set('id', link) |
|
92 | 100 | a = ElementTree.Element("a", {"class" : "anchor-link", "href" : "#" + link}) |
|
93 | 101 | a.text = u'ΒΆ' |
|
94 | 102 | h.append(a) |
|
95 | 103 | |
|
96 | 104 | # Known issue of Python3.x, ElementTree.tostring() returns a byte string |
|
97 | 105 | # instead of a text string. See issue http://bugs.python.org/issue10942 |
|
98 | 106 | # Workaround is to make sure the bytes are casted to a string. |
|
99 | 107 | return py3compat.decode(ElementTree.tostring(h), 'utf-8') |
|
100 | 108 | |
|
101 | 109 | |
|
102 | 110 | def add_prompts(code, first='>>> ', cont='... '): |
|
103 | 111 | """Add prompts to code snippets""" |
|
104 | 112 | new_code = [] |
|
105 | 113 | code_list = code.split('\n') |
|
106 | 114 | new_code.append(first + code_list[0]) |
|
107 | 115 | for line in code_list[1:]: |
|
108 | 116 | new_code.append(cont + line) |
|
109 | 117 | return '\n'.join(new_code) |
|
110 | 118 | |
|
111 | 119 | |
|
112 | 120 | def strip_dollars(text): |
|
113 | 121 | """ |
|
114 | 122 | Remove all dollar symbols from text |
|
115 | 123 | |
|
116 | 124 | Parameters |
|
117 | 125 | ---------- |
|
118 | 126 | text : str |
|
119 | 127 | Text to remove dollars from |
|
120 | 128 | """ |
|
121 | 129 | |
|
122 | 130 | return text.strip('$') |
|
123 | 131 | |
|
124 | 132 | |
|
125 | 133 | files_url_pattern = re.compile(r'(src|href)\=([\'"]?)files/') |
|
126 | 134 | |
|
127 | 135 | def strip_files_prefix(text): |
|
128 | 136 | """ |
|
129 | 137 | Fix all fake URLs that start with `files/`, |
|
130 | 138 | stripping out the `files/` prefix. |
|
131 | 139 | |
|
132 | 140 | Parameters |
|
133 | 141 | ---------- |
|
134 | 142 | text : str |
|
135 | 143 | Text in which to replace 'src="files/real...' with 'src="real...' |
|
136 | 144 | """ |
|
137 | 145 | return files_url_pattern.sub(r"\1=\2", text) |
|
138 | 146 | |
|
139 | 147 | |
|
140 | 148 | def comment_lines(text, prefix='# '): |
|
141 | 149 | """ |
|
142 | 150 | Build a Python comment line from input text. |
|
143 | 151 | |
|
144 | 152 | Parameters |
|
145 | 153 | ---------- |
|
146 | 154 | text : str |
|
147 | 155 | Text to comment out. |
|
148 | 156 | prefix : str |
|
149 | 157 | Character to append to the start of each line. |
|
150 | 158 | """ |
|
151 | 159 | |
|
152 | 160 | #Replace line breaks with line breaks and comment symbols. |
|
153 | 161 | #Also add a comment symbol at the beginning to comment out |
|
154 | 162 | #the first line. |
|
155 | 163 | return prefix + ('\n'+prefix).join(text.split('\n')) |
|
156 | 164 | |
|
157 | 165 | |
|
158 | 166 | def get_lines(text, start=None,end=None): |
|
159 | 167 | """ |
|
160 | 168 | Split the input text into separate lines and then return the |
|
161 | 169 | lines that the caller is interested in. |
|
162 | 170 | |
|
163 | 171 | Parameters |
|
164 | 172 | ---------- |
|
165 | 173 | text : str |
|
166 | 174 | Text to parse lines from. |
|
167 | 175 | start : int, optional |
|
168 | 176 | First line to grab from. |
|
169 | 177 | end : int, optional |
|
170 | 178 | Last line to grab from. |
|
171 | 179 | """ |
|
172 | 180 | |
|
173 | 181 | # Split the input into lines. |
|
174 | 182 | lines = text.split("\n") |
|
175 | 183 | |
|
176 | 184 | # Return the right lines. |
|
177 | 185 | return "\n".join(lines[start:end]) #re-join |
|
178 | 186 | |
|
179 | 187 | def ipython2python(code): |
|
180 | 188 | """Transform IPython syntax to pure Python syntax |
|
181 | 189 | |
|
182 | 190 | Parameters |
|
183 | 191 | ---------- |
|
184 | 192 | |
|
185 | 193 | code : str |
|
186 | 194 | IPython code, to be transformed to pure Python |
|
187 | 195 | """ |
|
188 | 196 | shell = InteractiveShell.instance() |
|
189 | 197 | return shell.input_transformer_manager.transform_cell(code) |
|
190 | 198 | |
|
191 | 199 | def posix_path(path): |
|
192 | 200 | """Turn a path into posix-style path/to/etc |
|
193 | 201 | |
|
194 | 202 | Mainly for use in latex on Windows, |
|
195 | 203 | where native Windows paths are not allowed. |
|
196 | 204 | """ |
|
197 | 205 | if os.path.sep != '/': |
|
198 | 206 | return path.replace(os.path.sep, '/') |
|
199 | 207 | return path |
|
200 | 208 | |
|
201 | 209 | def path2url(path): |
|
202 | 210 | """Turn a file path into a URL""" |
|
203 | 211 | parts = path.split(os.path.sep) |
|
204 | 212 | return '/'.join(quote(part) for part in parts) |
@@ -1,135 +1,140 b'' | |||
|
1 | 1 | """ |
|
2 | 2 | Module with tests for Strings |
|
3 | 3 | """ |
|
4 | 4 | |
|
5 | 5 | #----------------------------------------------------------------------------- |
|
6 | 6 | # Copyright (c) 2013, the IPython Development Team. |
|
7 | 7 | # |
|
8 | 8 | # Distributed under the terms of the Modified BSD License. |
|
9 | 9 | # |
|
10 | 10 | # The full license is in the file COPYING.txt, distributed with this software. |
|
11 | 11 | #----------------------------------------------------------------------------- |
|
12 | 12 | |
|
13 | 13 | #----------------------------------------------------------------------------- |
|
14 | 14 | # Imports |
|
15 | 15 | #----------------------------------------------------------------------------- |
|
16 | 16 | import os |
|
17 | 17 | |
|
18 | 18 | from ...tests.base import TestsBase |
|
19 | 19 | from ..strings import (wrap_text, html2text, add_anchor, strip_dollars, |
|
20 | 20 | strip_files_prefix, get_lines, comment_lines, ipython2python, posix_path, |
|
21 | 21 | add_prompts |
|
22 | 22 | ) |
|
23 | 23 | |
|
24 | 24 | |
|
25 | 25 | #----------------------------------------------------------------------------- |
|
26 | 26 | # Class |
|
27 | 27 | #----------------------------------------------------------------------------- |
|
28 | 28 | |
|
29 | 29 | class TestStrings(TestsBase): |
|
30 | 30 | |
|
31 | 31 | def test_wrap_text(self): |
|
32 | 32 | """wrap_text test""" |
|
33 | 33 | test_text = """ |
|
34 | 34 | Tush! never tell me; I take it much unkindly |
|
35 | 35 | That thou, Iago, who hast had my purse |
|
36 | 36 | As if the strings were thine, shouldst know of this. |
|
37 | 37 | """ |
|
38 | 38 | for length in [30,5,1]: |
|
39 | 39 | self._confirm_wrap_text(test_text, length) |
|
40 | 40 | |
|
41 | 41 | |
|
42 | 42 | def _confirm_wrap_text(self, text, length): |
|
43 | 43 | for line in wrap_text(text, length).split('\n'): |
|
44 | 44 | assert len(line) <= length |
|
45 | 45 | |
|
46 | 46 | |
|
47 | 47 | def test_html2text(self): |
|
48 | 48 | """html2text test""" |
|
49 | 49 | #TODO: More tests |
|
50 | 50 | self.assertEqual(html2text('<name>joe</name>'), 'joe') |
|
51 | 51 | |
|
52 | 52 | |
|
53 | 53 | def test_add_anchor(self): |
|
54 | 54 | """add_anchor test""" |
|
55 | 55 | #TODO: More tests |
|
56 | 56 | results = add_anchor('<b>Hello World!</b>') |
|
57 | 57 | assert 'Hello World!' in results |
|
58 | 58 | assert 'id="' in results |
|
59 | 59 | assert 'class="anchor-link"' in results |
|
60 | 60 | assert '<b' in results |
|
61 | 61 | assert '</b>' in results |
|
62 | 62 | |
|
63 | def test_add_anchor_fail(self): | |
|
64 | """add_anchor does nothing when it fails""" | |
|
65 | html = '<h1>Hello <br>World!</h1>' | |
|
66 | results = add_anchor(html) | |
|
67 | self.assertEqual(html, results) | |
|
63 | 68 | |
|
64 | 69 | def test_strip_dollars(self): |
|
65 | 70 | """strip_dollars test""" |
|
66 | 71 | tests = [ |
|
67 | 72 | ('', ''), |
|
68 | 73 | ('$$', ''), |
|
69 | 74 | ('$H$', 'H'), |
|
70 | 75 | ('$He', 'He'), |
|
71 | 76 | ('H$el', 'H$el'), |
|
72 | 77 | ('Hell$', 'Hell'), |
|
73 | 78 | ('Hello', 'Hello'), |
|
74 | 79 | ('W$o$rld', 'W$o$rld')] |
|
75 | 80 | for test in tests: |
|
76 | 81 | self._try_strip_dollars(test[0], test[1]) |
|
77 | 82 | |
|
78 | 83 | |
|
79 | 84 | def _try_strip_dollars(self, test, result): |
|
80 | 85 | self.assertEqual(strip_dollars(test), result) |
|
81 | 86 | |
|
82 | 87 | |
|
83 | 88 | def test_strip_files_prefix(self): |
|
84 | 89 | """strip_files_prefix test""" |
|
85 | 90 | tests = [ |
|
86 | 91 | ('', ''), |
|
87 | 92 | ('/files', '/files'), |
|
88 | 93 | ('test="/files"', 'test="/files"'), |
|
89 | 94 | ('My files are in `files/`', 'My files are in `files/`'), |
|
90 | 95 | ('<a href="files/test.html">files/test.html</a>', '<a href="test.html">files/test.html</a>')] |
|
91 | 96 | for test in tests: |
|
92 | 97 | self._try_files_prefix(test[0], test[1]) |
|
93 | 98 | |
|
94 | 99 | |
|
95 | 100 | def _try_files_prefix(self, test, result): |
|
96 | 101 | self.assertEqual(strip_files_prefix(test), result) |
|
97 | 102 | |
|
98 | 103 | |
|
99 | 104 | def test_comment_lines(self): |
|
100 | 105 | """comment_lines test""" |
|
101 | 106 | for line in comment_lines('hello\nworld\n!').split('\n'): |
|
102 | 107 | assert line.startswith('# ') |
|
103 | 108 | for line in comment_lines('hello\nworld\n!', 'beep').split('\n'): |
|
104 | 109 | assert line.startswith('beep') |
|
105 | 110 | |
|
106 | 111 | |
|
107 | 112 | def test_get_lines(self): |
|
108 | 113 | """get_lines test""" |
|
109 | 114 | text = "hello\nworld\n!" |
|
110 | 115 | self.assertEqual(get_lines(text, start=1), "world\n!") |
|
111 | 116 | self.assertEqual(get_lines(text, end=2), "hello\nworld") |
|
112 | 117 | self.assertEqual(get_lines(text, start=2, end=5), "!") |
|
113 | 118 | self.assertEqual(get_lines(text, start=-2), "world\n!") |
|
114 | 119 | |
|
115 | 120 | |
|
116 | 121 | def test_ipython2python(self): |
|
117 | 122 | """ipython2python test""" |
|
118 | 123 | #TODO: More tests |
|
119 | 124 | results = ipython2python(u'%%pylab\nprint("Hello-World")').replace("u'", "'") |
|
120 | 125 | self.fuzzy_compare(results, u"get_ipython().run_cell_magic('pylab', '', 'print(\"Hello-World\")')", |
|
121 | 126 | ignore_spaces=True, ignore_newlines=True) |
|
122 | 127 | |
|
123 | 128 | def test_posix_path(self): |
|
124 | 129 | """posix_path test""" |
|
125 | 130 | path_list = ['foo', 'bar'] |
|
126 | 131 | expected = '/'.join(path_list) |
|
127 | 132 | native = os.path.join(*path_list) |
|
128 | 133 | filtered = posix_path(native) |
|
129 | 134 | self.assertEqual(filtered, expected) |
|
130 | 135 | |
|
131 | 136 | def test_add_prompts(self): |
|
132 | 137 | """add_prompts test""" |
|
133 | 138 | text1 = """for i in range(10):\n i += 1\n print i""" |
|
134 | 139 | text2 = """>>> for i in range(10):\n... i += 1\n... print i""" |
|
135 | 140 | self.assertEqual(text2, add_prompts(text1)) |
General Comments 0
You need to be logged in to leave comments.
Login now